Data Science Plotly Visuals

library(tidyverse)

## ── Attaching packages ──────────────────────────────────────────────────────────────────────────────── tidyverse 1.2.1 ──

## ✔ ggplot2 3.2.1     ✔ purrr   0.3.3
## ✔ tibble  2.1.3     ✔ dplyr   0.8.3
## ✔ tidyr   1.0.0     ✔ stringr 1.4.0
## ✔ readr   1.3.1     ✔ forcats 0.4.0

## ── Conflicts ─────────────────────────────────────────────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag()    masks stats::lag()

library(viridis)

## Loading required package: viridisLite

library(p8105.datasets)
library(plotly)

## 
## Attaching package: 'plotly'

## The following object is masked from 'package:ggplot2':
## 
##     last_plot

## The following object is masked from 'package:stats':
## 
##     filter

## The following object is masked from 'package:graphics':
## 
##     layout

data("instacart")
insta_data = instacart %>%
  filter(department == "beverages") %>%
  mutate(reordered = recode(reordered, "1" = "Yes", "0" = "No"), 
         order_dow = recode(order_dow, "0" = "Sunday", "1" = "Monday", "2" = "Tuesday", 
                             "3" = "Wednesday", "4" = "Thursday", "5" = "Friday", "6" = "Saturday")) %>%
  select (aisle, product_name, order_hour_of_day, order_dow, reordered) 

count = insta_data %>% 
  group_by(aisle) %>%
  summarize(reordered = n())
count

## # A tibble: 8 x 2
##   aisle                         reordered
##   <chr>                             <int>
## 1 cocoa drink mixes                  1062
## 2 coffee                             8392
## 3 energy sports drinks               4742
## 4 juice nectars                     14350
## 5 refrigerated                      23228
## 6 soft drinks                       16279
## 7 tea                                9376
## 8 water seltzer sparkling water     36617

Bar Chart

• Number of times goods from each aisle were reorderd within the beverage department.

count %>%
  plot_ly(x = ~aisle, y = ~reordered, color = ~aisle, type = "bar", text = ~aisle) %>%
  layout(xaxis = list(title = "Aisle Category"),
         yaxis = list(title = "Total items reordered"))

Boxplot

• Distribution of each aisle being purchased across all hours of day.

insta_data %>%
  plot_ly(x = ~aisle, y = ~order_hour_of_day, color = ~aisle, type = "box") %>%
layout(xaxis = list(title = "Aisle Category"),
         yaxis = list(title = "Hour of Day Ordered"))

Line plot

• Number of times goods from each aisle were reorderd within the beverage department.